使用Keras进行整数系列预测 [英] Integer Series prediction using Keras
问题描述
我正在尝试编写一个RNN模型，该模型将预测整数序列中的下一个数字.模型损失在每个时期都会变小，但是预测永远不会变得非常准确.我已经尝试了许多火车的大小和时期，但是我的预测值总是与期望值相差几位数.您能否给我一些提示，以改进或我做错了什么?这是代码:
I'm trying to code a RNN model that will predict the next number in the integer series. The model loss gets smaller with each epoch, but the predictions never get quite accurate. I've tried many train set sizes and numbers of epochs, but my predicted value is always off from the expected by few digits. Can you give me some hints what to improve or what I'm doing wrong? This is the code:
from keras.models import Sequential
from keras.layers import Dense, Dropout, LSTM
from keras.callbacks import ModelCheckpoint
from keras.utils import np_utils
from keras import metrics
import numpy as np
training_length = 10000
rnn_size = 512
hm_epochs = 30
def generate_sequence(length=10):
step = np.random.randint(0,50)
first_element = np.random.randint(0,10)
first_element = 0
l_ist = [(first_element + (step*i)) for i in range(length)]
return l_ist
training_set = []
for _ in range(training_length):
training_set.append(generate_sequence(10))
feature_set = [i[:-1] for i in training_set]
label_set = [i[-1:] for i in training_set]
X = np.reshape(feature_set,(training_length, 9, 1))
y = np.array(label_set)
model = Sequential()
model.add(LSTM(rnn_size, input_shape = (X.shape[1], X.shape[2]), return_sequences = True))
model.add(Dropout(0.2))
model.add(LSTM(rnn_size))
model.add(Dropout(0.2))
model.add(Dense(y.shape[1], activation='linear'))
model.compile(loss='mse', optimizer='rmsprop', metrics=['accuracy'])
filepath="checkpoint_folder/weights-improvement.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min')
callbacks_list = [checkpoint]
model.fit(X,y,epochs=hm_epochs, callbacks=callbacks_list)
效果:
30个纪元后(亏损:66.39):
After 30 epochs (Loss: 66.39):
1顺序:[0，20，40，60，80，100，120，140，160]预期:[180] ||得到了:[181.86118]
1 Sequence: [0, 20, 40, 60, 80, 100, 120, 140, 160]Expected: [180] || Got: [181.86118]
2顺序:[0，11，22，33，44，55，66，77，88]预期:[99] ||得到了:[102.17369]
2 Sequence: [0, 11, 22, 33, 44, 55, 66, 77, 88]Expected: [99] || Got: [102.17369]
3顺序:[0，47，94，141，188，235，282，329，376]预计:[423] ||得到了:[419.1763]
3 Sequence: [0, 47, 94, 141, 188, 235, 282, 329, 376]Expected: [423] || Got: [419.1763]
4序列:[0，47，94，141，188，235，282，329，376]预计:[423] ||得到了:[419.1763]
4 Sequence: [0, 47, 94, 141, 188, 235, 282, 329, 376]Expected: [423] || Got: [419.1763]
5序列:[0，4，8，12，16，20，24，28，32]预期:[36] ||得到了:[37.506496]
5 Sequence: [0, 4, 8, 12, 16, 20, 24, 28, 32]Expected: [36] || Got: [37.506496]
6序列:[0，48，96，144，192，240，288，336，384]预期:[432] ||得到了:[425.0569]
6 Sequence: [0, 48, 96, 144, 192, 240, 288, 336, 384]Expected: [432] || Got: [425.0569]
7序列:[0，28，56，84，112，140，168，196，224]预计:[252] ||得到了:[253.60233]
7 Sequence: [0, 28, 56, 84, 112, 140, 168, 196, 224]Expected: [252] || Got: [253.60233]
8序列:[0，18，36，54，72，90，108，126，144]预期:[162] ||得到了:[163.538]
8 Sequence: [0, 18, 36, 54, 72, 90, 108, 126, 144]Expected: [162] || Got: [163.538]
9序列:[0，19，38，57，76，95，114，133，152]预期:[171] ||得到了:[173.77933]
9 Sequence: [0, 19, 38, 57, 76, 95, 114, 133, 152]Expected: [171] || Got: [173.77933]
10序列:[0，1，2，3，4，5，6，7，8]预期:[9] ||得到了:[9.577981]
10 Sequence: [0, 1, 2, 3, 4, 5, 6, 7, 8]Expected: [9] || Got: [9.577981]
...
100个周期后(亏损:54.81):
After 100 epochs (Loss: 54.81):
1顺序:[0，20，40，60，80，100，120，140，160]预期值:[180] ||得到了:[181.03535]
1 Sequence: [0, 20, 40, 60, 80, 100, 120, 140, 160] Expected: [180] || Got: [181.03535]
2顺序:[0，11，22，33，44，55，66，77，88]预期值:[99] ||得到了:[99.15022]
2 Sequence: [0, 11, 22, 33, 44, 55, 66, 77, 88] Expected: [99] || Got: [99.15022]
3序列:[0，47，94，141，188，235，282，329，376]预期值:[423] ||得到了:[423.7969]
3 Sequence: [0, 47, 94, 141, 188, 235, 282, 329, 376] Expected: [423] || Got: [423.7969]
4序列:[0，47，94，141，188，235，282，329，376]预期值:[423] ||得到了:[423.7969]
4 Sequence: [0, 47, 94, 141, 188, 235, 282, 329, 376] Expected: [423] || Got: [423.7969]
5序列:[0，4，8，12，16，20，24，28，32]预期值:[36] ||得到了:[34.47298]
5 Sequence: [0, 4, 8, 12, 16, 20, 24, 28, 32] Expected: [36] || Got: [34.47298]
6序列:[0，48，96，144，192，240，288，336，384]预期值:[432] ||得到了:[432.73163]
6 Sequence: [0, 48, 96, 144, 192, 240, 288, 336, 384] Expected: [432] || Got: [432.73163]
7序列:[0，28，56，84，112，140，168，196，224]预期值:[252] ||得到了:[251.55792]
7 Sequence: [0, 28, 56, 84, 112, 140, 168, 196, 224] Expected: [252] || Got: [251.55792]
8序列:[0，18，36，54，72，90，108，126，144]预期值:[162] ||得到了:[164.81227]
8 Sequence: [0, 18, 36, 54, 72, 90, 108, 126, 144] Expected: [162] || Got: [164.81227]
9序列:[0，19，38，57，76，95，114，133，152]预期值:[171] ||得到了:[172.6425]
9 Sequence: [0, 19, 38, 57, 76, 95, 114, 133, 152] Expected: [171] || Got: [172.6425]
10序列:[0、1、2、3、4、5、6、7、8]预期值:[9] ||得到了:[8.837313]
10 Sequence: [0, 1, 2, 3, 4, 5, 6, 7, 8] Expected: [9] || Got: [8.837313]
推荐答案
关于您的示例，您的输入序列仅为(x 2x 3x)等. 对于递归神经网络这不是问题.您想学习一种计算策略，而不是功能上的长期依赖. RNN非常强大，可以找到非常复杂的模式，但为此，它们不是正确的工具.
Regarding your examples your input sequence is just (x 2x 3x) etc. This is not a problem for recurrent neural networks. You want to learn a calculation policy, not long term dependecies in features. RNNs are very powerful and can find very complex pattern, but for this they are not the right tool.
要解决此问题，您可以看一下进化算法.
To solve such a problem you can take a look at evolutionary algorithms.
这篇关于使用Keras进行整数系列预测的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
